Physically Based Rendering in the Latent Space
Computer Graphics Forum · 13.11.2026
DOI: 10.1111/cgf.70633 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 13.11.2026. Verfasst von Vuk Radovanovic und 3 weiteren Autor:innen. Die Arbeit nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Image diffusion models have shown impressive image generation capabilities but are often hard to control, in contrast to classical computer graphics pipelines such as physically based rendering. However, we observe that there is a bridge between light transport phenomena and the distribution of latent space values produced by such models. Thus, we introduce physically based rendering in the feature space learned by the variational autoencoders in generative models, enabling light transport simulation in the latent space. This allows us to leverage physically based rendering techniques to output latent maps for physically guided content generation. We propose modifications to the rendering equation, which, when paired with a differentiable renderer, can yield an optimal set of scene parameters that require only minimal refinement to accurately render into the pretrained latent space. We train our method on a single rendered image, and then demonstrate the generalization of the method to scene geometry changes, lighting changes, and camera view changes.
Zitieren
APA
Radovanovic, V., Gupta, V., Gruson, A., & Hua, B. (2026). Physically Based Rendering in the Latent Space. Computer Graphics Forum. https://doi.org/10.1111/cgf.70633
Vancouver
Radovanovic V, Gupta V, Gruson A, Hua B. Physically Based Rendering in the Latent Space. Computer Graphics Forum. 2026. doi:10.1111/cgf.70633
BibTeX
@article{Radovanovic2026,
author = {Radovanovic, Vuk and Gupta, Vishesh and Gruson, Adrien and Hua, Binh‐Son},
title = {Physically Based Rendering in the Latent Space},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70633}
}
EUVIMED